Specialty Paper Mill Improves First-Pass Retention and Reduces Raw Material Consumption Using Mt. Fuji AI
Haber deployed Mt. Fuji®, its predictive industrial AI platform, to optimize Retention & Drainage Aid (RDA) dosing at one of India's largest specialty paper manufacturers. By continuously predicting retention performance and prescribing optimal polymer dosage, Mt. Fuji increased first-pass retention, reduced raw material consumption, and improved overall paper quality while lowering operating costs.
The Challenge
Retention and drainage directly influence paper machine efficiency, product quality, and raw material utilization. Poor retention allows valuable fibers and fillers to pass through the wire with white water, increasing raw material losses while negatively impacting drainage, machine stability, and sheet formation.
The mill experienced:
- Low first-pass retention
- Excessive fiber and filler losses
- High polymer consumption
- Increased raw material costs
- Variable sheet quality
- Reduced drainage efficiency
Manual dosing strategies could not respond effectively to changing furnish conditions, leading to inconsistent performance and unnecessary chemical consumption.
Haber's Approach
Mt. Fuji continuously monitored stock consistency, flow rates, filler loading, white-water characteristics, production rate, and key process variables affecting retention performance.
AI models predicted first-pass retention in real time, identifying process conditions likely to increase fiber losses before they impacted production.
Mt. Fuji prescribed the optimal Retention & Drainage Aid dosage based on current process conditions, ensuring maximum fiber retention with minimum polymer consumption.
Self-learning AI models continuously adapted to changes in furnish composition, production rates, and machine operating conditions, improving optimization performance over time.
Evidence-Backed Results
| Metric | Before | After | Change |
|---|---|---|---|
| First-pass retention | 71% | 75% | 5.6% increase |
| Raw material consumption | 70 TPP | 67 TPD | 4.3% reduction |
| Annual operating savings | - | ₹3.7 million | Lower Raw Material Cost |
Business Impact
By replacing manual polymer dosing with predictive AI optimization, Mt. Fuji improved fiber retention while reducing raw material losses across the paper machine.
Conclusion
Mt. Fuji transformed retention and drainage control from a manually adjusted operation into an intelligent predictive optimization system. By continuously prescribing optimal polymer dosage, the platform improved first-pass retention, reduced raw material consumption, and delivered substantial cost savings while enhancing paper quality.
